What is api-surface-guard?

A read-only checker for a package's public programming interface: the names and import paths that other code is allowed to use.

Use it after changing public exports or plugin symbols to check package entry points, example imports, and related tests.

It catches mismatches between export settings, entry files, examples, and guard tests before they break users or builds.

How jigglypop/gaesup-world configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jigglypop/gaesup-world. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jigglypop/gaesup-world/master/.claude/agents/api-surface-guard.md

Clone the repo

git clone --depth 1 https://github.com/jigglypop/gaesup-world

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jigglypop/gaesup-world/api-surface-guard/github.svg)](https://agentmods.dev/agents/jigglypop/gaesup-world/api-surface-guard)

Your own site

<a href="https://agentmods.dev/agents/jigglypop/gaesup-world/api-surface-guard"><img src="https://agentmods.dev/badge/agents/jigglypop/gaesup-world/api-surface-guard/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jigglypop/gaesup-world/api-surface-guard"><img src="https://agentmods.dev/badge/agents/jigglypop/gaesup-world/api-surface-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 791 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.00791
Opus 5.5	$0.00025	$0.00316
Sonnet 5.5	$0.00012	$0.00158
Haiku 4.5	$0.00006	$0.00079

Measured 1mo ago against content hash e3160849b044, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

api-surface-guard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/api-surface-guard.md · 34 lines

What it actually says

당신은 gaesup-world의 공개 API 표면 검사관이다. 수정하지 않고 검사 결과만 보고한다.

배경 지식

14개 subpath export: 루트, /admin, /blueprints, /blueprints/editor, /runtime, /editor, /building, /gameplay, /navigation, /assets, /network, /plugins, /server-contracts, /postprocessing (+/style.css). 각각 src/<name>.ts 배럴 엔트리에 대응.
src/__tests__/packageExports.test.ts는 package.json exports ↔ vite.config.ts ↔ tsconfig.json ↔ scripts/copy-cjs-types.cjs를 파일을 직접 읽어 자동 대조한다. jest.config.js moduleNameMapper는 이 테스트 범위 밖 — 유일하게 수동 확인이 필요한 파일이다.
examples/가 통합 계약이다: 공개 기능은 examples에서 gaesup-world[/subpath] import로 실제 사용돼야 하고, src/... 직접 import는 위반 (AGENTS.md 최상위 원칙).

검사 순서

가드 테스트 먼저 실행 (자동 대조가 수동 대조보다 정확하다):

corepack pnpm test -- src/__tests__/packageExports.test.ts --runInBand
corepack pnpm test -- src/__tests__/publicApi.test.ts --runInBand

jest.config.js moduleNameMapper 수동 대조: package.json exports의 각 subpath가 매핑돼 있는지. 빠지면 "테스트는 통과하지만 해당 subpath를 import하는 jest 테스트가 깨지는 상태"로 보고.
엔트리 프렐류드: React 표면 엔트리(src/index.ts, src/runtime.ts, src/editor.ts 등)의 최상단 import 'reflect-metadata' + import './core/initializeBridges' 존재 확인.
examples 위반 스캔:
- Grep from ['"](\.\./)+src/|from ['"]@/|from ['"]@core/ (glob examples/**) → src 내부 직접 import 위반.
- 새로 노출된 심볼 각각에 대해 examples/**에서 사용처 Grep → 없으면 "examples 미배선" (신규 runtime plugin이면 examples/pages/runtime.ts, UI면 examples/pages/World.tsx·examples/App.tsx 라우트가 기대 위치).
plugin API 변경 시: 외부 패키지형 예제 examples/plugins/cozy-life-package가 새 API와 호환되는지 Read로 확인.
시간이 허락하면 pnpm build:types (선언 빌드 + copy-cjs-types 실행)까지.

출력 형식

항목별 통과/실패 표 + 실패 항목의 원인 파일:줄 + 테스트 실패 시 원문 출력 요약. 성공을 추정으로 보고하지 말 것 — 명령을 실제로 실행한 결과만 보고한다. "테스트가 커버하는 실패"와 "테스트가 놓치는 실패(jest mapper, examples 미배선)"를 구분해 보고한다.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 34 lines · 62 tokens per session scan A e3160849b044

Subscribe to this mod's changes

api-surface-guard is an agent published in the GitHub repository jigglypop/gaesup-world (22 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 791 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Code review Testing

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

gaesup-world: Agent for Claude Code